Semi-Parametric Efficient Policy Learning with Continuous Actions

Mert Demirer, Vasilis Syrgkanis, Greg Lewis and Victor Chernozhukov
Additional contact information
Mert Demirer: Institute for Fiscal Studies
Vasilis Syrgkanis: Institute for Fiscal Studies
Greg Lewis: Institute for Fiscal Studies

No CWP34/19, CeMMAP working papers from Centre for Microdata Methods and Practice, Institute for Fiscal Studies

Abstract: We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space. Our work extends prior approaches of policy optimization from observational data that only considered discrete actions. We provide an experimental evaluation of our method in a synthetic data example motivated by optimal personalized pricing and costly resource allocation.

Date: 2019-06-12
New Economics Papers: this item is included in nep-ecm
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (14)

Downloads: (external link)
https://www.ifs.org.uk/uploads/CW3419_Semi-Paramet ... ntinuous_Actions.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 404 Not Found (https://www.ifs.org.uk/uploads/CW3419_Semi-Parametric_Efficient_Policy_Learning_with_Continuous_Actions.pdf [302 Found]--> https://ifs.org.uk/uploads/CW3419_Semi-Parametric_Efficient_Policy_Learning_with_Continuous_Actions.pdf)

Related works:
Working Paper: Semi-Parametric Efficient Policy Learning with Continuous Actions (2019)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ifs:cemmap:34/19

Ordering information: This working paper can be ordered from
The Institute for Fiscal Studies 7 Ridgmount Street LONDON WC1E 7AE

Access Statistics for this paper

More papers in CeMMAP working papers from Centre for Microdata Methods and Practice, Institute for Fiscal Studies The Institute for Fiscal Studies 7 Ridgmount Street LONDON WC1E 7AE. Contact information at EDIRC.
Bibliographic data for series maintained by Emma Hyman ().